This repository was archived by the owner on Jan 19, 2026. It is now read-only.
Conversation
- Add langgraph, litellm, langfuse, instructor deps to pyproject - Scaffold agentic module dirs: providers, models, workflows, observability - Add provider config and Ollama health checks - Add Langfuse initialization helper - Add failing integration test skeleton for basic AI workflow - Mark completed tasks in specs/001-agentic-ai-corrector/tasks.md
… tests done feat(models): implement agentic data models and enums (T017–T023 groundwork) chore(dev): add jiwer and promptfoo dev deps
…er scaffolds - Base provider interface and LiteLLM-based bridge - Pydantic schemas for CorrectionProposal (+list) - Agent and rules-based router scaffolds - Correction workflow scaffold - Update tasks to reflect completed items
…stores
- POST /api/v1/correction/agentic
- GET /api/v1/correction/session/{id}
- POST /api/v1/feedback
- GET/PUT /api/v1/models
- GET /api/v1/metrics
Update tasks to mark API endpoints completed.
…path in v1 - Add USE_AGENTIC_AI flag metadata in correction results - Return fallback response when preferred model unavailable
…sponse - Export env flags for downstream usage - Return JSONResponse 503 for unavailable model - Mark CLI task T064 complete
- FeedbackStore with minimal sessions/feedback tables - Persist v1 session and feedback records when available - Mark T069 and T070 complete
…hecks - Stub agent proposal test - Skip API-dependent tests when server not running - Validate models and metrics endpoints shape
…tests - Session-scoped fixture spins up server if possible - Keeps API tests from skipping when frontend assets available
…1/metrics feat(agent): optional Instructor schema enforcement path docs(tasks): mark T043, T068 complete
…r bridge feat(workflows): minimal LangGraph correction graph and agent hook docs(tasks): mark T066, T077, T029 complete
…rappers docs(tasks): mark T025–T028 complete
- Record fallback and success events with minimal metadata
- Build linear position map; prompt agent and adapt proposals to WordCorrection - Controlled by USE_AGENTIC_AI and AGENTIC_AI_MODEL
docs(tasks): mark T031, T045, T046 complete
…ard components docs(tasks): mark T048–T050 complete
…ocs tasks - README Agentic AI usage, provider keys, observability - Provider config environment validation helper - Mark T057, T058, T074 complete
… smoke test docs(tasks): mark T063 complete
…angGraph, with working LangFuse observability
…make frontend compatible but needs rework to make UX actually good and mobile friendly
Updated dependencies
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.